Chunking German Legal Code

TL;DR

This study evaluates various chunking strategies for legal document retrieval in German law, finding that structure-aligned methods outperform complex semantic approaches in recall and efficiency.

Contribution

It systematically compares multiple chunking approaches for legal retrieval, emphasizing the importance of domain-specific structure preservation.

Findings

Structure-aligned chunking achieves highest recall.

Simpler methods are more computationally efficient.

Complex semantic methods underperform compared to structural approaches.

Abstract

This paper investigates chunking strategies for retrieval-augmented generation on German statutory law, using the German Civil Code as a structured benchmark corpus. We implement and compare a range of segmentation approaches, including structural units (sections, subsections, sentences, propositions), fixed-size windows, contextual chunking, semantic clustering, Lumber-style chunking, and RAPTOR-based hierarchical retrieval. All methods are evaluated on a legal question-answering dataset with section-level gold labels, measuring recall, query latency, index build time, and storage requirements. Results show that chunking strategies aligned with the inherent legal structure - particularly section and subsection - based retrieval-achieve the highest recall, while more complex approaches that override this structure perform worse. These simpler methods also offer favorable computational efficiency compared to LLM-intensive techniques such as contextual chunking, RAPTOR, and Lumber. The findings highlight a key trade-off between semantic enrichment and operational cost, and demonstrate that preserving domain-specific structure is critical for effective legal information retrieval.